English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Gait of a person refers to his/her walking pattern, and according to medicalstudies gait of every individual is unique. Over the past decade, severalcomputer vision-based gait recognition approaches have been proposed in whichwalking information corresponding to a complete gait cycle has been used toconstruct gait features for person identification. These methods compute gaitfeatures with the inherent assumption that a complete gait cycle is alwaysavailable. However, in most public places occlusion is an inevitableoccurrence, and due to this, only a fraction of a gait cycle gets captured bythe monitoring camera. Unavailability of complete gait cycle informationdrastically affects the accuracy of the extracted features, and till date, onlya few occlusion handling strategies to gait recognition have been proposed. Butnone of these performs reliably and robustly in the presence of a single cyclewith incomplete information, and because of this practical application of gaitrecognition is quite limited. In this work, we develop deep learning-basedalgorithm to accurately identify the affected frames as well as predict themissing frames to reconstruct a complete gait cycle. While occlusion detectionhas been carried out by employing a VGG-16 model, the model for framereconstruction is based on Long-Short Term Memory network that has been trainedto optimize a multi-objective function based on dice coefficient andcross-entropy loss. The effectiveness of the proposed occlusion reconstructionalgorithm is evaluated by computing the accuracy of the popular Gait EnergyFeature on the reconstructed sequence. Experimental evaluation on public datasets and comparative analysis with other occlusion handling methods verify theeffectiveness of our approach.

RGait-NET: An Effective Network for Recovering Missing Information from Occluded Gait Cycles